OpenAI Codex
ProductOpenAI Codex is a large language model developed by OpenAI for translating natural-language prompts into source code. Announced in 2021, it was a modified production version of GPT-3 that was fine-tuned on source code in multiple programming languages, and it served as the original model for GitHub Copilot.
From Wikipedia, licensed under CC BY-SA 4.0. Shown as published there.
Facts
- Made by
- OpenAISource: Wikidata
- First released
- 2025Source: Wikidata
- Latest version
- 5.3 (2026)Source: Wikidata
- Wikipedia
- Read on WikipediaSource: Wikidata
Am I affected?
Checked against NVD affected-version data on our server. Nothing you type is stored.
Security timeline
- Vulnerability reported by Help Net SecurityEmbedded browsers in five AI coding assistants allow code execution, file theft and address spoofing
Recent news
Check Point finds jailbreak bundle for Codex that injects adverts into agent files
Check Point Research analysed the Haiou jailbreak bundle for OpenAI Codex, which uses prompt injection and role-play to bypass guardrails and installs security-focused skills. The package also modifies Codex configuration files to inject adverts for an OpenAI-compatible LLM gateway into later responses, which the researchers classify as prompt adware. A threat actor running Cobalt Strike was found using the bundle alongside Ladon and VulnClaw.
Embedded browsers in five AI coding assistants allow code execution, file theft and address spoofing
Forever Security reported flaws in the embedded browsers of Cursor, GitHub Copilot, OpenAI Codex, VS Code and Claude Desktop, grouped under the name EMBRACE. Impacts include code execution in Cursor, address-bar spoofing in Copilot, and local file reads in Codex, VS Code and Claude Desktop, including SSH keys, .env files and npm tokens. Cursor and Copilot have been fixed, while Codex and VS Code were unpatched at publication.